Skip to content
View joshuaswarren's full-sized avatar
46 followers · 4 following

Achievements

Achievement: Pull Sharkx4Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: YOLOAchievement: Arctic Code Vault ContributorAchievement: Starstruck

Achievements

Achievement: Pull Sharkx4Achievement: Pair Extraordinairex4Achievement: QuickdrawAchievement: YOLOAchievement: Arctic Code Vault ContributorAchievement: Starstruck

Highlights

Block or report joshuaswarren

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
joshuaswarren/README.md

Joshua Warren

I build human-agent systems for real-world work.

My focus is user-aware agents: AI systems that remember responsibly, understand user context, model intent, learn preferences, and get useful work done with fewer unnecessary interruptions.

Current work

  • Remnic — open-source memory and context for user-aware agents
  • Agentic commerce — AI agents, product data, checkout, ERP, and commerce operations
  • Embedded AI-enabled commerce delivery — AI-native delivery for Magento and Adobe Commerce teams

Remnic

Remnic explores the systems layer around user-aware agents:

  • scoped memory
  • provenance
  • retrieval quality
  • correction
  • boundaries
  • evals
  • ask-versus-act decisions
  • MCP / HTTP access
  • Codex CLI, Claude Code, Replit, and other agent integrations

The goal is simple: agents that understand the people they work with well enough to help without constantly interrogating them.

Background

I’ve spent 25+ years shipping commerce systems: development, architecture, deployment, client-facing strategy, Magento and Adobe Commerce, ERP integrations, release hygiene, developer education, and founder/operator work.

During the Magento 2 transition, I spoke at 20+ conferences helping developers understand and deploy a major platform shift. AI agents are the next version of that pattern: powerful technology that needs practical workflows, clear boundaries, and real-world deployment discipline.

Useful links

Pinned Loading

  1. remnic remnic Public

    Open-source memory and context for user-aware agents: scoped memory, provenance, retrieval quality, correction, boundaries, evals, and MCP/HTTP access.

    TypeScript 73 11

  2. openclaw-langsmith openclaw-langsmith Public

    LangSmith tracing plugin for OpenClaw. Automatic observability for agent turns, tool calls, and LLM invocations.

    TypeScript 6 2

  3. openclaw-atlas openclaw-atlas Public

    Atlas - Enterprise document indexing plugin for OpenClaw. Vectorless RAG using PageIndex with async indexing, incremental updates, and smart caching. Scales from 10 to 5000+ documents. Perfect for …

    TypeScript 5

  4. pageindex-ts pageindex-ts Public

    TypeScript reimplementation of PageIndex - vectorless, reasoning-based document search using LLM traversal. MIT-licensed alternative to Python PageIndex for Node.js applications.

    TypeScript 5